A review of tree-based approaches for anomaly detection
Abstract Data-driven Anomaly Detection approaches have received increasing attention in
many application areas in the past few years as a tool to monitor complex systems in …
many application areas in the past few years as a tool to monitor complex systems in …
An applicable predictive maintenance framework for the absence of run-to-failure data
D Kim, S Lee, D Kim - Applied Sciences, 2021 - mdpi.com
As technology advances, the equipment becomes more complicated, and the importance of
the Prognostics and Health Management (PHM) to monitor the condition of the equipment …
the Prognostics and Health Management (PHM) to monitor the condition of the equipment …
Voltage stability monitoring based on disagreement-based deep learning in a time-varying environment
The traditional learning based static voltage stability monitoring methods require manual
labeling of a large number of training samples. Getting these labeled training sets is …
labeling of a large number of training samples. Getting these labeled training sets is …
Online Detection of Events With Low-Quality Synchrophasor Measurements Based on Forest
In this article, we propose an online datadriven approach that leverages the isolation
mechanism for fast event detection with low-quality data measurement. The proposed …
mechanism for fast event detection with low-quality data measurement. The proposed …
Detecting and locating cyber and physical stresses in smart grids using the k‐nearest neighbour analysis of instantaneous correlation of states
MA Hasnat, M Rahnamay‐Naeini - IET Smart Grid, 2021 - Wiley Online Library
Monitoring the state of smart grids and detecting abnormalities are challenging tasks due to
their large size, distributed nature, and complex and stochastic dynamics. Large deployment …
their large size, distributed nature, and complex and stochastic dynamics. Large deployment …
Missing data recovery in large power systems using network embedding
This paper proposes a novel network-embedding based method to recover the missing
measurements in power systems. In particular, we first construct the spatial and temporal …
measurements in power systems. In particular, we first construct the spatial and temporal …
PEDI-GAN: power equipment data imputation based on generative adversarial networks with auxiliary encoder
Smart grids commonly rely on analyzing sensor data to monitor power equipment. However,
these sensor data can suffer varying levels of loss or corruption due to complex …
these sensor data can suffer varying levels of loss or corruption due to complex …
Monitoring of a platinum group metal flotation plant with an isolation forest
Froth flotation is one of the most important techniques in mineral processing to beneficiate
valuable minerals from ore. As a consequence, advanced control of industrial flotation plants …
valuable minerals from ore. As a consequence, advanced control of industrial flotation plants …
Improving Anomaly Detection for Industrial Applications
T Barbariol - 2023 - research.unipd.it
Negli ultimi dieci anni la disponibilità di grandi quantità di dati e potenza di calcolo ha spinto
la comunità scientifica verso lo sviluppo di algoritmi capaci di imparare autonomamente dai …
la comunità scientifica verso lo sviluppo di algoritmi capaci di imparare autonomamente dai …
A data driven detection and locating of cyber and physical stresses in smart grid based on state correlations
MA Hasnat, M Rahnamay-Naeini - 2019 9th International …, 2019 - ieeexplore.ieee.org
Smart grids being complex cyber-physical infrastructures demand real-time monitoring of
their dynamic states. Phasor measurement units (PMUs) are smart metering devices with a …
their dynamic states. Phasor measurement units (PMUs) are smart metering devices with a …